Filters








39,879 Hits in 5.3 sec

Hardware-Based Hopfield Neuromorphic Computing for Fall Detection

Zheqi Yu, Adnan Zahid, Shuja Ansari, Hasan Abbas, Amir M. Abdulghani, Hadi Heidari, Muhammad A. Imran, Qammer H. Abbasi
2020 Sensors  
For example, traditional machine-learning methods for data classification, especially in real time, are computationally intensive.  ...  Through simulations, the classification accuracy of the fall data reached 88.9% which compares well with some other results achieved by the software-based machine-learning algorithms, which verify the  ...  Authors would also like to thank Sultan Qaboos University (Government of the Sultanate of Oman) for supporting Amir M. Abdulghani.  ... 
doi:10.3390/s20247226 pmid:33348587 fatcat:ebsdfw4neradfhxqdutzd4wmma

EEG-based Classification of Drivers Attention using Convolutional Neural Network [article]

Fred Atilla, Maryam Alimardani
2021 arXiv   pre-print
Our findings show that CNN and raw EEG signals can be employed for effective training of a passive BCI for real-time attention classification.  ...  Using their EEG signals, we trained three attention classifiers; a support vector machine (SVM) using EEG spectral band powers, and a Convolutional Neural Network (CNN) using either spectral features or  ...  Future research should attempt to examine the performance of deep learning models in real-time driving or in Virtual Reality simulations where richer feedback is present [24] .  ... 
arXiv:2108.10062v1 fatcat:dmu74zramffz5hxdtjocra4szy

Survey of Object Detection using Deep Neural Networks

Mrs. Swetha M S, Mr. Muneshwara M S, Dr. Thungamani M
2018 IJARCCE  
Object detection was previously done using only conventional deep convolution neural network whereas using regional based convolution network [3] increases the accuracy and also decreases the time required  ...  Object detection using deep neural network especially convolution neural networks.  ...  Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World The paper explores domain randomization, a simple but promising method for addressing the reality gap.  ... 
doi:10.17148/ijarcce.2018.71104 fatcat:4scb7v7lovgrjj4vhkxlyfvx2y

Editorial for the Special Issue "Advanced Machine Learning for Time Series Remote Sensing Data Analysis"

Gwanggil Jeon, Valerio Bellandi, Abdellah Chehri
2020 Remote Sensing  
In principal, this edition of the Special Issue is focused on time series data processing for remote sensing applications with special emphasis on advanced machine learning platforms.  ...  After review, a total of eight papers have been accepted for publication in this issue.  ...  Finally, we would like to express our sincere gratitude to Journal Staffs and Assistant Editor, for providing us with this unique opportunity to present our work in MDPI Remote Sensing.  ... 
doi:10.3390/rs12172815 fatcat:6xopnjvbbfdxxeg3nrfwiobmbm

Artificial Neural Network and Its Application Research Progress in Chemical Process [article]

Li Sun, Fei Liang, Wutai Cui
2021 arXiv   pre-print
Artificial neural network (ANN) is a systematic structure composed of multiple neuron models. Its main function is to simulate multiple basic functions of the nervous system of living organisms.  ...  This article will introduce the basic principles and development history of artificial neural networks, and review its application research progress in chemical process control, fault diagnosis, and process  ...  At the same time, through the real-time feedback of the feedback network, the information can be transmitted to various areas, and the content of the information can be output in the form of data, and  ... 
arXiv:2110.09021v1 fatcat:zbkgxxpjsbcgxbp6vt4mwqr2za

Machine learning for modeling, diagnostics, and control of non-equilibrium plasmas

Ali Mesbah, David B Graves
2019 Journal of Physics D: Applied Physics  
This paper presents our perspectives on how ML can potentially transform modeling and simulation, real-time monitoring, and control of NEP.  ...  Machine learning (ML) is a set of computational tools that can analyze and utilize large amounts of data for many different purposes.  ...  The advent of deep neural network architectures has transformed reinforcement learning applications by significantly increasing their real-time learning capabilities.  ... 
doi:10.1088/1361-6463/ab1f3f fatcat:zdmlxj2jn5b6dj23purms2r7xq

Behavioural pattern identification and prediction in intelligent environments

Sawsan Mahmoud, Ahmad Lotfi, Caroline Langensiepen
2013 Applied Soft Computing  
The results presented here are validated using data generated from a simulator and real environments.  ...  The experimental results show that non-linear autoregressive network with exogenous inputs model correctly extracts the long term prediction patterns of the occupant and outperformed the Elman network.  ...  In [24] and [25] a temporal neural-network based embedded agent is used which can work with real-time data from unobtrusive low-level sensors and actuators.  ... 
doi:10.1016/j.asoc.2012.12.012 fatcat:c6lk7wyauvarxn6br7n7xi75ju

A Journal of Real Peak Recognition of Electrocardiogram (ECG) Signals Using Neural Network

Tarmizi Amani Izzah
2013 American Journal of Networks and Communications  
Result obtained showing that neural network pattern recognition is able to classify and recognize the real peaks accordingly with overall accuracy of 81.6% although there might be limitations and misclassification  ...  These features will then be fed as an input to neural network system. The target output represented real peaks of the signals is also being defined using a binary number.  ...  Syed Sahal Nazli Alhady for provides endless help including motivation and guidance and also not forget to co-supervisor as well as field supervisor for some supported ideas directly or indirectly.  ... 
doi:10.11648/j.ajnc.20130201.12 fatcat:4vx2j7k6mzh4piwpyqraq2cwya

A Dual-Stream Recurrent Neural Network for Student Feedback Prediction using Kinect

Shanfeng Hu, Hindol Bhattacharya, Matangini Chattopadhyay, Nauman Aslam, Hubert P. H. Shum
2018 2018 12th International Conference on Software, Knowledge, Information Management & Applications (SKIMA)  
Such classifications can give a better, dynamic and real-time feedback of the actual emotional reaction of the learner towards the learning module.  ...  A subject's image of the facial expression during learning can be analysed and a deep learning neural network can be trained to categorize the facial expression into one of the multiple emotion classes  ...  Keywords: feedback prediction, Kinect, convolutional neural networks (CNNs), recurrent neural networks (RNNs), deep learning, e-Learning I.  ... 
doi:10.1109/skima.2018.8631537 dblp:conf/skima/HuBCAS18 fatcat:onjqlbnkonagpnyvbcjcp5wsei

Feedback Techniques in Computer-Based Simulation Training: A Survey [article]

Sudanthi Wijewickrema, Xingjun Ma, James Bailey, Gregor Kennedy and Stephen O'Leary
2017 arXiv   pre-print
Here, we explore the provision of feedback in CBST from three perspectives: 1) types of feedback to be provided, 2) presentation modalities of feedback, and 3) methods for feedback extraction/learning.  ...  Typically, CBST systems comprise of two essential components: 1) a simulation environment that provides an immersive and interactive learning experience, and 2) a feedback intervention system that supports  ...  The adversarial property of neural networks has been explored recently to extract feedback for simulation-based learning [54] .  ... 
arXiv:1705.04683v1 fatcat:4xnythfnzrdd5k6t7knfmjkfzu

A Symbiotic Brain-Machine Interface through Value-Based Decision Making

Babak Mahmoudi, Justin C. Sanchez, Josh Bongard
2011 PLoS ONE  
Methodology: The control architecture designed was based on Actor-Critic learning, which is a PARC-based reinforcement learning method.  ...  for adaptation of the decoder with high precision.  ...  Jose Principe for helpful discussions. Author Contributions  ... 
doi:10.1371/journal.pone.0014760 pmid:21423797 pmcid:PMC3056711 fatcat:t7onn6wmj5eedonsptkzl66o3y

Mining Historical Traffic Data using Back Propagation Neural Network for Accurate Location Estimation

Rakesh Verma, Abhay Kothari
2015 International Journal of Computer Applications  
The presented improvement helps in initializing neural network and frequent learning. Therefore, the neural network is effectively trained in less amount of time with higher accuracy.  ...  During implementation of neural network based predictive algorithm two key deficiencies are observed first the long training time and quality of training patterns.  ...  Using the trace the node movement is extracted for training and with respect to real time data the neural network's predictive performance of algorithm is evaluated.  ... 
doi:10.5120/19344-0467 fatcat:7izkifbp55f5jbg6aynkmm3wgy

Artificial Neural Network and Its Application Research Progress in Chemical Process

Li Sun, Fei Liang, Wutai Cui
2021 Asian Journal of Research in Computer Science  
Artificial neural network is a systematic structure composed of multiple neuron models.  ...  By simulating many basic functions of the nervous system of living organisms, nonlinear control can be realized without relying on mathematical models, and it is especially suitable for more complex control  ...  At the same time, through the real-time feedback of the feedback network, the information can be transmitted to various areas, and the content of the information can be output in the form of data, and  ... 
doi:10.9734/ajrcos/2021/v12i430302 fatcat:xwor7kaqa5hfnfugol24vrzeaa

Comparison between MLP and LVQ Neural Networks for Virtual Upper Limb Prosthesis Control [chapter]

Daniel Caetano, Fernando Mattioli, Kenedy Nogueira, Edgard Lamounier, Alexandre Cardoso
2012 Lecture Notes in Computer Science  
For this reason, artificial neural networks have been explored to be applied in the training phase to provide real time response.  ...  To achieve this, different feature extraction techniques for simulation and control of virtual prostheses are investigated. 1  ...  Artificial neural network (ANN) are systems that can recognize and classify patterns, such as EMG, from a learning model based on human learning [2] .  ... 
doi:10.1007/978-3-642-32639-4_47 fatcat:6vedagjydngrnpsjpcqdg52jwa

Servo Health Monitoring Based on Feature Learning via Deep Neural Network

Yajing Zhou, Yuemin Zheng, Jin Tao, Mingwei Sun, Qinglin Sun, Matthias Dehmer, Zengqiang Chen
2021 IEEE Access  
According to the test simulation time data in Table 7 , when neural network structure 2 is used, and the learning rate is 0.00001, the running time of single test data is the shortest.  ...  This paper considers both frequency domain and abstract domain for fault diagnosis. In the paper, a feature learning based health monitoring method using a deep neural network is proposed.  ...  In addition, this paper mainly uses deep neural networks to monitor the health status of servo and determine the fault degree.  ... 
doi:10.1109/access.2021.3132046 fatcat:tdc44qt7svey5po3yxzshlkbsy
« Previous Showing results 1 — 15 out of 39,879 results